No abstract

We observed that the correlation among the major oculometric parameters and their individual contribution to hyperopia in esotropic children were similar in amblyopic and non-amblyopic eyes. This finding suggests that the counterbalancing effect of greater corneal and lens power associated with shorter axial length is similar in both eyes of patients with esotropic amblyopia.

INTRODUÇÃOUma das questões mais difíceis no tratamento do estrabismo consiste no planejamento da estratégia cirúrgica. Além do conhecimento científico, a experiência do cirurgião tem participação fundamental na decisão desta etapa, devido, em parte, à grande variabilidade observada em situações clínicas aparentemente semelhantes (1) .Recentemente, a inteligência artificial vem sendo utilizada como uma ferramenta de auxílio diagnóstico na área médica. Como exemplo podemos citar os programas para interpretação de eletrocardiogramas, que atualmente apresentam performance comparável à de um cardiologista (2) . A rede neural artificial (RNA), uma forma de inteligência artificial, consiste na simulação, através de "software" ou "hardware", de alguns aspectos do sistema nervoso biológico, na tentativa de permitir a realização de tarefas Uso da rede neural artificial no planejamento cirúrgico da correção do estrabismo Objetivo: Desenvolver uma rede neural artificial para planejar a estratégia cirúrgica em pacientes portadores de estrabismo sensorial, com desvio horizontal. Métodos: Foi realizado estudo retrospectivo envolvendo 95 pacientes portadores de estrabismo sensorial, atendidos no Ambulatório de Motilidade Ocular Extrínseca do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo. Foi construída uma rede neural artificial utilizando-se o Java Neural Network 1.1. Foram utilizados 68 pacientes para treinamento e validação da rede e 27 para testar o seu funcionamento. Resultados: Dos 68 pacientes utilizados no treinamento da rede, 37 apresentavam exotropia e 31 esotropia. O método utilizado para treinamento da rede foi o "backpropagation". A taxa de aprendizado utilizada foi de 0,6, e a taxa de tolerância de erro 0,05. Dos 27 pacientes utilizados para avaliação da eficácia da rede, 18 apresentavam exotropia, e 9 esotropia. A eficácia da rede foi avaliada pela média da diferença entre os resultados fornecidos pela rede, e as indicações originais. Nos pacientes com exotropia o erro médio foi de 0,4 mm (±0,4), para o retrocesso do músculo reto lateral, e de 0,3 mm (±0,3), para a ressecção do músculo reto medial. Nas esotropias, o erro médio foi de 0,2 mm (±0,2), para o retrocesso do músculo reto medial e de 0,5 mm (±0,3), para ressecção do músculo reto lateral. Conclusão: A rede neural artificial, por sua característica de simular o sistema nervoso central biológico, e sua capacidade de realizar tarefas cognitivas, é opção viável para auxiliar no planejamento cirúrgico da correção do estrabismo.

Uncorrected refractive errors are the leading cause of visual impairment in children. In this crosssectional retrospective study, we analyzed a social visual screening program for school children in Sã o Paulo, Brazil, evaluated its impact on the prevention and treatment of children's visual disabilities, and assessed its epidemiological outcomes to outline suggestions for its improvement. METHODS: First-grade children from public schools were submitted to prior visual screening by their teachers. Selected children were forwarded to the hospital's campaigns for a second screening by ophthalmologists and treatment if needed. Data were analyzed for age, sex, visual acuity, biomicroscopy, refractive errors, ocular movement disorders, amblyopia, number of donated spectacles, and number of children forwarded to specialized care. RESULTS: A total of 1080 children were included with mean age of 6.24 ± 0.45 years. Children with normal ophthalmological exam, 591 (54.7%; 95% confidence interval [CI]: 51.7%-57.7%) were dismissed and considered false-positives. Myopia, hyperopia, and astigmatism components were found in 164 (15.2%; CI: 13.1%-17.4%), 190 (17.6%; CI: 15.3%-20.0%), and 330 (30.5%; CI: 27.8%-33.4%) children, respectively. Amblyopia was diagnosed in 54 (5%; CI: 3.5%-6.4%) children, and 117 (10.8%; CI: 9.8%-12.8%) presented ocular movement disorders. A total of 420 glasses were donated. CONCLUSION: Epidemiological findings for amblyopia and refractive errors are consistent with those of similar studies. The expressive number of diagnoses performed and number of glasses donated to underprivileged children depict the importance of such projects. New guidelines to improve their cost-effectiveness, such as professional training and community sensitization, are imperative.

The study showed that compliance with patching plays a fundamental role in therapeutic efficacy. Thus, age at the beginning of treatment alone did not influence the success rate since it was possible to obtain good compliance independent of age. In addition, worse results were associated with severe amblyopia and less compliance.

Silent sinus syndrome is an acquired condition in which there is a gradual collapse of the orbital floor and inward retraction of the maxillary sinus (atelectasis of the maxillary sinus). This in turn may cause associated ocular occurrences of enophthalmos and hypotropia. This is a report of an 8 year-old boy with silent sinus syndrome and associated ocular motility disorders. The association between silent sinus syndrome and ocular motility disturbance has been recently described in the literature. However, this is an infrequent association, mainly in childhood.

Purpose Clinical evaluation of eye versions plays an important role in the diagnosis of special strabismus. Despite the importance of versions, they are not standardized in clinical practice because they are subjective. Assuming that objectivity confers accuracy, this research aims to create an artificial intelligence app that can classify the eye versions into nine positions of gaze. Methods We analyzed photos of 110 strabismus patients from an outpatient clinic of a tertiary hospital at nine gazes. For each photo, the gaze was identified, and the corresponding version was rated by the same examiner during patient evaluation. Results The images were standardized by using the OpenCV library in Python language, so that the patient's eyes were located and sent to a multilabel model through the Keras framework regardless of the photo orientation. Then, the model was trained for each combination of the following groupings: eyes (left, right), gaze (1 to 9), and version (−4 to 4). Resnet50 was used as the neural network architecture, and the Data Augmentation technique was applied. For quick inference via web browser, the SteamLit app framework was employed. For use in Mobiles, the finished model was exported for use in through the Tensorflow Lite converter. Conclusions The results showed that the mobile app might be applied to complement evaluation of ocular motility based on objective classification of ocular versions. However, further exploratory research and validations are required. Translational Relevance Apart from the traditional clinical practice method, professionals will be able to envisage an easy-to-apply support app, to increase diagnostic accuracy.

No abstract